数据下载

wkdir=`pwd`
mkdir $wkdir/data
cd $wkdir/data
prefetch SRR13195578 SRR13195579 SRR13195580 SRR13195581 SRR13195582 SRR13195583 SRR13195584 SRR13195585 SRR13195586 SRR13195587 SRR13195588 SRR13195589 --max-size u
cd SRR13195578/
fasterq-dump SRR13195578.sra

https://www.ncbi.nlm.nih.gov/bioproject/682443

https://www.ncbi.nlm.nih.gov/bioproject/?term=GSE162640

质控

mkdir $wkdir/1_qc
cd $wkdir/1_qc
sample="SRR13195578"
fastp \
  -i $wkdir/data/${sample}/${sample}_1.fastq \
  -I $wkdir/data/${sample}/${sample}_2.fastq \
  -o ${sample}_1.fp.fq.gz \
  -O ${sample}_2.fp.fq.gz \
  -j ${sample}.json \
  -h ${sample}.html \
  &> ${sample}.fp.log

比对

方法一（Bowtie2）

构建索引

mkdir $wkdir/2_mapping_bowtie2
cd $wkdir/2_mapping_bowtie2
mkdir ref
bowtie2-build \
  $wkdir/ncbi_dataset/data/GCF_000001735.4/GCF_000001735.4_TAIR10.1_genomic.fna \
  ref/genome \
  &> bowtie2-build.log

比对

bowtie2 \
  -x $wkdir/2_mapping/ref/genome \
  -1 $wkdir/1_qc/${sample}_1.fp.fq.gz \
  -2 $wkdir/1_qc/${sample}_2.fp.fq.gz \
  -S ${sample}.sam \
  -p 4 \
  1> ${sample}_bowtie2_align.log \
  2> ${sample}_bowtie2_align.err

方法二（BWA）

构建索引

mkdir $wkdir/2_mapping_bwa
cd $wkdir/2_mapping_bwa
mkdir ref

比对

bwa mem \
  -M reference_genome.fa \
  sample1_R1_trimmed.fq \
  sample1_R2_trimmed.fq \
  > sample1_aligned.sam

过滤

方法一（picard）

排序

mkdir $wkdir/3_filter_picard
cd $wkdir/3_filter_picard
samtools view \
  ${sample}.sam \
  -Sb \
  -q 20 | \
  samtools sort \
  -o ${sample}_sorted.bam \
  -@ 4 \
  &> ${sample}_sort_bam.log

过滤

去除PCR重复

java -jar picard.jar MarkDuplicates \
  I=${sample}_sorted.bam \
  O=${sample}_aligned_dedup.bam \
  M=${sample}_duplicate_metrics.txt \
  REMOVE_DUPLICATES=true \
  &> ${sample}_picard.log
# $EBROOTPICARD/picard.jar

方法二（deepTools）

mkdir $wkdir/3_filter_deeptools
cd $wkdir/3_filter_deeptools

参考

1. 手把手教你学ChIP-seq数据分析 3
2. ChIP-seq数据比对实战